@inproceedings{porada-etal-2026-osynth,
title = "{OS}ynth: A Longitudinal, Context-Sensitive Evaluation of Meeting Understanding",
author = "Porada, Ian and
Tripathi, Suraj and
Animesh, Chaitanya and
Sari, Leda and
Narisetty, Chaitanya and
Matthews, Austin R and
Yu, Bohan and
Thulasiram, Ramesh L and
Sell, Gregory and
Chin, KK and
Genzel, Dmitriy",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-main.2277/",
pages = "51783--51813",
ISBN = "979-8-89176-459-0",
abstract = "Meeting notetakers are increasingly deployed in settings where longitudinal context is available including calendar metadata, prior meetings, emails, slides, and speaker enrollments; however, meeting corpora remain limited in terms of size, domain coverage, and available context. We present OSynth, a large-scale synthetic dataset of simulated organizations comprising 570 hours of meeting audio together with associated artifacts and a latent ground-truth state. In a pairwise comparison, human raters distinguish OSynth meetings from real meeting transcripts with only 56{\%} accuracy based on excerpts of 150{--}300 words. Across state-of-the-art LLMs, additional context yields significant gains on several entity-sensitive dimensions, demonstrating limitations of contemporary approaches and the potential usefulness of OSynth in developing better-contextualized meeting-understanding systems."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="porada-etal-2026-osynth">
<titleInfo>
<title>OSynth: A Longitudinal, Context-Sensitive Evaluation of Meeting Understanding</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ian</namePart>
<namePart type="family">Porada</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Suraj</namePart>
<namePart type="family">Tripathi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chaitanya</namePart>
<namePart type="family">Animesh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leda</namePart>
<namePart type="family">Sari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chaitanya</namePart>
<namePart type="family">Narisetty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Austin</namePart>
<namePart type="given">R</namePart>
<namePart type="family">Matthews</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bohan</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ramesh</namePart>
<namePart type="given">L</namePart>
<namePart type="family">Thulasiram</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gregory</namePart>
<namePart type="family">Sell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">K</namePart>
<namePart type="given">K</namePart>
<namePart type="family">Chin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dmitriy</namePart>
<namePart type="family">Genzel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-459-0</identifier>
</relatedItem>
<abstract>Meeting notetakers are increasingly deployed in settings where longitudinal context is available including calendar metadata, prior meetings, emails, slides, and speaker enrollments; however, meeting corpora remain limited in terms of size, domain coverage, and available context. We present OSynth, a large-scale synthetic dataset of simulated organizations comprising 570 hours of meeting audio together with associated artifacts and a latent ground-truth state. In a pairwise comparison, human raters distinguish OSynth meetings from real meeting transcripts with only 56% accuracy based on excerpts of 150–300 words. Across state-of-the-art LLMs, additional context yields significant gains on several entity-sensitive dimensions, demonstrating limitations of contemporary approaches and the potential usefulness of OSynth in developing better-contextualized meeting-understanding systems.</abstract>
<identifier type="citekey">porada-etal-2026-osynth</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.2277/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>51783</start>
<end>51813</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T OSynth: A Longitudinal, Context-Sensitive Evaluation of Meeting Understanding
%A Porada, Ian
%A Tripathi, Suraj
%A Animesh, Chaitanya
%A Sari, Leda
%A Narisetty, Chaitanya
%A Matthews, Austin R.
%A Yu, Bohan
%A Thulasiram, Ramesh L.
%A Sell, Gregory
%A Chin, K. K.
%A Genzel, Dmitriy
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F porada-etal-2026-osynth
%X Meeting notetakers are increasingly deployed in settings where longitudinal context is available including calendar metadata, prior meetings, emails, slides, and speaker enrollments; however, meeting corpora remain limited in terms of size, domain coverage, and available context. We present OSynth, a large-scale synthetic dataset of simulated organizations comprising 570 hours of meeting audio together with associated artifacts and a latent ground-truth state. In a pairwise comparison, human raters distinguish OSynth meetings from real meeting transcripts with only 56% accuracy based on excerpts of 150–300 words. Across state-of-the-art LLMs, additional context yields significant gains on several entity-sensitive dimensions, demonstrating limitations of contemporary approaches and the potential usefulness of OSynth in developing better-contextualized meeting-understanding systems.
%U https://aclanthology.org/2026.emnlp-main.2277/
%P 51783-51813
Markdown (Informal)
[OSynth: A Longitudinal, Context-Sensitive Evaluation of Meeting Understanding](https://aclanthology.org/2026.emnlp-main.2277/) (Porada et al., EMNLP 2026)
ACL
- Ian Porada, Suraj Tripathi, Chaitanya Animesh, Leda Sari, Chaitanya Narisetty, Austin R Matthews, Bohan Yu, Ramesh L Thulasiram, Gregory Sell, KK Chin, and Dmitriy Genzel. 2026. OSynth: A Longitudinal, Context-Sensitive Evaluation of Meeting Understanding. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 51783–51813, Budapest, Hungary. Association for Computational Linguistics.